Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8eec4546ef50e0170a8f1f58ba9c1e048c56d34d3dcbd4a511ddcc9db8859f
+oid sha256:4f34e33ba1cbed0160af5c5593143e3e8b38e70fe96482a2977d0f63263da34f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1cc149ce5a2c9671fb85284f09886d7a8abce3fc0a2014044d0f02d1f022dc2
+oid sha256:23c67de520f57e300affbc221b1aae6fd0aa44e79e593afad93c33f9d2772417
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db130484859ac18bcc59d3f63a2034b920c3187ab4ad8631498050925a77bb9
+oid sha256:1bc72a2dd61fde2bf7e35b38e131fc7660ee3fdebf98f8b23ba292ea3eb99170
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5663836002349854,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.14571948998178508,
+  "best_metric": 2.531459331512451,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.2185792349726776,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,13 +35,27 @@
       "eval_samples_per_second": 29.8,
       "eval_steps_per_second": 3.729,
       "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 2.5398,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 2.531459331512451,
+      "eval_runtime": 245.5646,
+      "eval_samples_per_second": 25.549,
+      "eval_steps_per_second": 3.197,
+      "step": 300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5859971699097600.0,
+  "total_flos": 8808208295362560.0,
   "trial_name": null,
   "trial_params": null
 }